| { |
| "add_faster_video": false, |
| "add_time_instruction": false, |
| "architectures": [ |
| "LlavaQwenForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_internvl_chat.InternVLChatConfig", |
| "AutoModel": "modeling_internvl_chat.InternVLChatModel", |
| "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel" |
| }, |
| "downsample_ratio": 0.5, |
| "dtype": "bfloat16", |
| "dynamic_image_size": true, |
| "eos_token_id": 151645, |
| "faster_token_stride": 10, |
| "force_image_size": 448, |
| "force_sample": false, |
| "hidden_act": "silu", |
| "hidden_size": 3584, |
| "image_aspect_ratio": "anyres_max_9", |
| "image_crop_resolution": null, |
| "image_fold": null, |
| "image_grid_pinpoints": [ |
| [ |
| 224, |
| 224 |
| ], |
| [ |
| 224, |
| 448 |
| ], |
| [ |
| 224, |
| 672 |
| ], |
| [ |
| 224, |
| 896 |
| ], |
| [ |
| 224, |
| 1120 |
| ], |
| [ |
| 224, |
| 1344 |
| ], |
| [ |
| 448, |
| 224 |
| ], |
| [ |
| 448, |
| 448 |
| ], |
| [ |
| 448, |
| 672 |
| ], |
| [ |
| 448, |
| 896 |
| ], |
| [ |
| 448, |
| 1120 |
| ], |
| [ |
| 448, |
| 1344 |
| ], |
| [ |
| 672, |
| 224 |
| ], |
| [ |
| 672, |
| 448 |
| ], |
| [ |
| 672, |
| 672 |
| ], |
| [ |
| 672, |
| 896 |
| ], |
| [ |
| 672, |
| 1120 |
| ], |
| [ |
| 672, |
| 1344 |
| ], |
| [ |
| 896, |
| 224 |
| ], |
| [ |
| 896, |
| 448 |
| ], |
| [ |
| 896, |
| 672 |
| ], |
| [ |
| 896, |
| 896 |
| ], |
| [ |
| 896, |
| 1120 |
| ], |
| [ |
| 896, |
| 1344 |
| ], |
| [ |
| 1120, |
| 224 |
| ], |
| [ |
| 1120, |
| 448 |
| ], |
| [ |
| 1120, |
| 672 |
| ], |
| [ |
| 1120, |
| 896 |
| ], |
| [ |
| 1120, |
| 1120 |
| ], |
| [ |
| 1120, |
| 1344 |
| ], |
| [ |
| 1344, |
| 224 |
| ], |
| [ |
| 1344, |
| 448 |
| ], |
| [ |
| 1344, |
| 672 |
| ], |
| [ |
| 1344, |
| 896 |
| ], |
| [ |
| 1344, |
| 1120 |
| ], |
| [ |
| 1344, |
| 1344 |
| ] |
| ], |
| "image_split_resolution": null, |
| "initializer_range": 0.02, |
| "intermediate_size": 18944, |
| "layer_types": [ |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention" |
| ], |
| "llm_config": { |
| "_attn_implementation_autoset": true, |
| "_name_or_path": "./pretrained/Qwen2.5-32B-Instruct", |
| "architectures": [ |
| "Qwen2ForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "dtype": "bfloat16", |
| "eos_token_id": 151643, |
| "hidden_act": "silu", |
| "hidden_size": 3584, |
| "initializer_range": 0.02, |
| "intermediate_size": 18944, |
| "layer_types": [ |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 32768, |
| "max_window_layers": 70, |
| "model_type": "qwen2", |
| "moe_config": null, |
| "num_attention_heads": 28, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 4, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": { |
| "factor": 2.0, |
| "rope_type": "dynamic", |
| "type": "dynamic" |
| }, |
| "rope_theta": 1000000.0, |
| "sliding_window": null, |
| "use_bfloat16": true, |
| "use_cache": false, |
| "use_sliding_window": false, |
| "vocab_size": 151674 |
| }, |
| "max_dynamic_patch": 12, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 70, |
| "min_dynamic_patch": 1, |
| "mm_hidden_size": 1024, |
| "mm_newline_position": "grid", |
| "mm_patch_merge_type": "spatial_unpad", |
| "mm_projector_lr": null, |
| "mm_projector_type": "mlp2x_gelu", |
| "mm_resampler_type": null, |
| "mm_spatial_pool_mode": "bilinear", |
| "mm_spatial_pool_stride": null, |
| "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_vision_resampler,mm_language_model", |
| "mm_use_im_patch_token": false, |
| "mm_use_im_start_end": false, |
| "mm_vision_select_feature": "patch", |
| "mm_vision_select_layer": -2, |
| "mm_vision_tower": "openai/clip-vit-large-patch14", |
| "mm_vision_tower_lr": null, |
| "model_type": "internvl_chat", |
| "moe_config": null, |
| "num_attention_heads": 28, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 4, |
| "output_attentions": false, |
| "pad2square": false, |
| "pad_token_id": 151643, |
| "pos_skipping_range": 4096, |
| "ps_version": "v2", |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 1000000.0, |
| "select_layer": -1, |
| "sliding_window": null, |
| "system_message": null, |
| "template": "internvl2_5", |
| "tie_word_embeddings": false, |
| "tokenizer_model_max_length": 13000, |
| "tokenizer_padding_side": "right", |
| "transformers_version": null, |
| "use_backbone_lora": 0, |
| "use_cache": true, |
| "use_llm_lora": 0, |
| "use_mm_proj": true, |
| "use_pos_skipping": false, |
| "use_sliding_window": false, |
| "use_thumbnail": true, |
| "vision_config": { |
| "_attn_implementation_autoset": true, |
| "_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5", |
| "architectures": [ |
| "InternVisionModel" |
| ], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_intern_vit.InternVisionConfig", |
| "AutoModel": "modeling_intern_vit.InternVisionModel" |
| }, |
| "capacity_factor": 1.2, |
| "drop_path_rate": 0.1, |
| "dropout": 0.0, |
| "dtype": "bfloat16", |
| "eval_capacity_factor": 1.4, |
| "hidden_act": "gelu", |
| "hidden_size": 1024, |
| "image_size": 448, |
| "initializer_factor": 0.1, |
| "initializer_range": 1e-10, |
| "intermediate_size": 4096, |
| "laux_allreduce": "all_nodes", |
| "layer_norm_eps": 1e-06, |
| "model_type": "intern_vit_6b", |
| "moe_coeff_ratio": 0.5, |
| "moe_intermediate_size": 768, |
| "moe_output_scale": 4.0, |
| "noisy_gate_policy": "RSample_before", |
| "norm_type": "layer_norm", |
| "num_attention_heads": 16, |
| "num_channels": 3, |
| "num_experts": 8, |
| "num_hidden_layers": 24, |
| "num_routed_experts": 4, |
| "num_shared_experts": 4, |
| "patch_size": 14, |
| "qk_normalization": false, |
| "qkv_bias": true, |
| "shared_expert_intermediate_size": 3072, |
| "use_bfloat16": true, |
| "use_flash_attn": true, |
| "use_moe": false, |
| "use_residual": true, |
| "use_rts": false, |
| "use_weighted_residual": false |
| }, |
| "vision_tower_pretrained": null, |
| "vocab_size": 151674 |
| } |
|
|
